INDEX

Explanations

statements relating to assessments or corrections

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows questions or statements

np_acts-logits-general · gemini-2.0-flash

correct diagnosis, reported control, by answering

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.96

 समीक्षाओं

-0.82

AddTagHelper

-0.77

 виправивши

-0.77

 فريبيس

-0.76

 CreateTagHelper

-0.75

ViewImports

-0.75

 NSCoder

-0.72

SourceChecksum

-0.72

ⓧ

-0.70

POSITIVE LOGITS

 näm

0.78

 importantly

0.69

 claro

0.62

Zitat

0.60

 however

0.60

 sûr

0.59

 moreover

0.58

 infatti

0.57

 Indeed

0.56

 needless

0.56

Activations Density 0.929%

statements relating to assessments or corrections

Follows questions or statements

correct diagnosis, reported control, by answering

No Comments

No Known Activations